File size: 4,169 Bytes
f55d1bb c8b64c4 f55d1bb c8b64c4 f55d1bb e58dcf1 f55d1bb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 |
---
language:
- "th"
tags:
- "thai"
- "question-answering"
- "dependency-parsing"
datasets:
- "universal_dependencies"
license: "apache-2.0"
pipeline_tag: "question-answering"
widget:
- text: "กว่า"
context: "หลายหัวดีกว่าหัวเดียว"
- text: "หลาย"
context: "หลายหัวดีกว่าหัวเดียว"
- text: "หัว"
context: "หลาย[MASK]ดีกว่าหัวเดียว"
---
# deberta-base-thai-ud-head
## Model Description
This is a DeBERTa(V2) model pretrained on Thai Wikipedia texts for dependency-parsing (head-detection on Universal Dependencies) as question-answering, derived from [deberta-base-thai](https://huggingface.co/KoichiYasuoka/deberta-base-thai). Use [MASK] inside `context` to avoid ambiguity when specifying a multiple-used word as `question`.
## How to Use
```py
from transformers import AutoTokenizer,AutoModelForQuestionAnswering,QuestionAnsweringPipeline
tokenizer=AutoTokenizer.from_pretrained("KoichiYasuoka/deberta-base-thai-ud-head")
model=AutoModelForQuestionAnswering.from_pretrained("KoichiYasuoka/deberta-base-thai-ud-head")
qap=QuestionAnsweringPipeline(tokenizer=tokenizer,model=model,align_to_words=False)
print(qap(question="กว่า",context="หลายหัวดีกว่าหัวเดียว"))
```
or (with [ufal.chu-liu-edmonds](https://pypi.org/project/ufal.chu-liu-edmonds/))
```py
class TransformersUD(object):
def __init__(self,bert):
import os
from transformers import (AutoTokenizer,AutoModelForQuestionAnswering,
AutoModelForTokenClassification,AutoConfig,TokenClassificationPipeline)
self.tokenizer=AutoTokenizer.from_pretrained(bert)
self.model=AutoModelForQuestionAnswering.from_pretrained(bert)
x=AutoModelForTokenClassification.from_pretrained
if os.path.isdir(bert):
d,t=x(os.path.join(bert,"deprel")),x(os.path.join(bert,"tagger"))
else:
from transformers.file_utils import hf_bucket_url
c=AutoConfig.from_pretrained(hf_bucket_url(bert,"deprel/config.json"))
d=x(hf_bucket_url(bert,"deprel/pytorch_model.bin"),config=c)
s=AutoConfig.from_pretrained(hf_bucket_url(bert,"tagger/config.json"))
t=x(hf_bucket_url(bert,"tagger/pytorch_model.bin"),config=s)
self.deprel=TokenClassificationPipeline(model=d,tokenizer=self.tokenizer,
aggregation_strategy="simple")
self.tagger=TokenClassificationPipeline(model=t,tokenizer=self.tokenizer)
def __call__(self,text):
import numpy,torch,ufal.chu_liu_edmonds
w=[(t["start"],t["end"],t["entity_group"]) for t in self.deprel(text)]
z,n={t["start"]:t["entity"].split("|") for t in self.tagger(text)},len(w)
r,m=[text[s:e] for s,e,p in w],numpy.full((n+1,n+1),numpy.nan)
v,c=self.tokenizer(r,add_special_tokens=False)["input_ids"],[]
for i,t in enumerate(v):
q=[self.tokenizer.cls_token_id]+t+[self.tokenizer.sep_token_id]
c.append([q]+v[0:i]+[[self.tokenizer.mask_token_id]]+v[i+1:]+[[q[-1]]])
b=[[len(sum(x[0:j+1],[])) for j in range(len(x))] for x in c]
with torch.no_grad():
d=self.model(input_ids=torch.tensor([sum(x,[]) for x in c]),
token_type_ids=torch.tensor([[0]*x[0]+[1]*(x[-1]-x[0]) for x in b]))
s,e=d.start_logits.tolist(),d.end_logits.tolist()
for i in range(n):
for j in range(n):
m[i+1,0 if i==j else j+1]=s[i][b[i][j]]+e[i][b[i][j+1]-1]
h=ufal.chu_liu_edmonds.chu_liu_edmonds(m)[0]
if [0 for i in h if i==0]!=[0]:
i=([p for s,e,p in w]+["root"]).index("root")
j=i+1 if i<n else numpy.nanargmax(m[:,0])
m[0:j,0]=m[j+1:,0]=numpy.nan
h=ufal.chu_liu_edmonds.chu_liu_edmonds(m)[0]
u="# text = "+text.replace("\n"," ")+"\n"
for i,(s,e,p) in enumerate(w,1):
p="root" if h[i]==0 else "dep" if p=="root" else p
u+="\t".join([str(i),r[i-1],"_",z[s][0][2:],"_","|".join(z[s][1:]),
str(h[i]),p,"_","_" if i<n and e<w[i][0] else "SpaceAfter=No"])+"\n"
return u+"\n"
nlp=TransformersUD("KoichiYasuoka/deberta-base-thai-ud-head")
print(nlp("หลายหัวดีกว่าหัวเดียว"))
```
|